A token communication framework for MLLMs sends compressed image latents and reconstructs them as both an image prior and adapter-injected visual tokens, improving task performance at low bitrates.
Token communications: A large model-driven framework for cross-modal context-aware semantic communications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SP 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Token Communication for Multimodal Large Language Model
A token communication framework for MLLMs sends compressed image latents and reconstructs them as both an image prior and adapter-injected visual tokens, improving task performance at low bitrates.